2026-07-27

AREX: Towards a Recursively Self-Improving Agent for Deep Research

👍 139

07/23 08:00

Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed into tractable constraint-wise checks. This discovery--verification asymmetry suggests that a research agent should do mo

中文介绍 提出AREX，一种递归自我改进的深度研究代理，利用发现-验证不对称性：生成候选答案成本高，但验证可分解为约束检查。代理通过自我反思和迭代优化提升搜索效率，在复杂约束任务中表现优于传统方法。

SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD

👍 58

07/22 08:00

Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed training, including severe memory pressure, non-overlapped communication overhead, and inefficient kernel execution. While most large-scale LLM training syst

中文介绍 针对万亿参数MoE模型全参数后训练的系统挑战，提出SLAI T-Rex，在Ascend SuperPOD上实现高效分布式训练。通过内存优化、通信重叠与内核加速，解决了大规模训练中的内存压力和通信开销问题。

K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs

👍 57

07/23 08:00

Large language models are increasingly used in K-12 education, but existing benchmarks mainly test exam question answering rather than understanding how curriculum knowledge is structured and visually presented. We call this capability curriculum cognition. It covers prerequisite chains, concept tax

中文介绍 提出K12-KGraph，一个与课程对齐的知识图谱，用于基准测试和训练教育LLM。涵盖先修链、概念分类等课程认知能力，提供结构化知识表示以评估模型对课程内容的理解和可视化呈现，超越传统问答基准。

ReferTrack: Referring Then Tracking for Embodied Visual Tracking

👍 49

07/22 08:00

Embodied visual tracking (EVT) requires a mobile agent to continuously follow a specific target described in natural language using only onboard vision. While recent vision-language-action (VLA) policies unify target identification and trajectory planning, their chain-of-thought (CoT) reasoning ofte

中文介绍 提出ReferTrack，针对具身视觉跟踪任务，将目标识别与轨迹规划解耦。先通过语言描述定位目标，再执行跟踪，避免VLA策略中CoT推理的歧义。在仿真环境中实现更精准的持续跟踪。

Visual Contrastive Self-Distillation

👍 43

07/23 08:00

On-policy self-distillation (OPSD) is promising as it removes the external teacher required by on-policy distillation (OPD), yet it still needs asymmetric information between teacher and student to ensure that the self-teacher provides a stronger learning signal than the student. Existing methods cr

中文介绍 提出视觉对比自蒸馏（VCSD），通过在像素空间和表示空间引入对比学习，在不需外部教师的情况下增强自蒸馏信号。在图像分类和目标检测任务上，VCSD优于现有自蒸馏方法，并接近有教师蒸馏性能。

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text

👍 35

07/23 08:00

Spatial intelligence is essential for agents to move from static semantic understanding toward interacting with the physical world. Many spatial tasks are grounded in continuous visual scenes, where locations, regions, and paths are more naturally expressed by pointing, marking, or drawing than by r

中文介绍 针对空间智能评估，提出以视觉生成像素而非文本输出进行评价的方法。通过让模型在图像中标记、绘制路径等方式测试其空间认知，相比LLM文本形式更贴近真实场景，发现当前多模态模型在连续空间推理上仍有显著不足。

Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

👍 29

07/22 08:00

As large language models and AI agents become the primary consumers of search results, document set quality determines the upper bound of downstream generation. Yet existing evaluation systems remain confined to scoring documents independently and aggregating via nDCG, ignoring inter-document intera

中文介绍 超越相关性检索，提出基于评分标准的文档集合选择与排序方法。考虑文档间的交互影响，而非独立打分，优化整集合质量以提升下游LLM生成上限。在多个搜索基准上，该方法优于nDCG聚合方案。

NVIDIA-labs OO Agents: Native Python Object-Oriented Agents

👍 26

07/22 08:00

Traditional agent development is split across prompt templates, tool schemas, callback code, and workflow graphs. We present NVIDIA Object-Oriented Agents (NOOA), a model-agnostic Python framework for building reliable AI agents. NOOA takes a simpler approach: an agent is a Python object. Its method

中文介绍 提出NVIDIA对象导向代理（NOOA），一个Python框架。将代理视为Python对象，方法为工具、属性为状态，通过原生OOP范式统一提示模板、工具schema与工作流，简化开发并提高可靠性。

An Exam for Active Observers

👍 25

07/17 08:00

Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot. Decades of psychophysics and cognitive science have argued that this active observation is essential for a wide range of tasks. Whether today's multimodal large language models (M

中文介绍 设计主动观察考试，评估多模态大语言模型（MLLM）在闭环视觉中的表现。通过动态注视引导任务，发现当前MLLM无法有效利用中间假设重定向视线，远不及人类主动观察能力，揭示了模型在动态场景理解上的根本缺陷。

LLMs Get Lost in Evolving User Intent

👍 21

07/22 08:00

As LLMs become more capable, they are increasingly deployed as collaborative agents, taking on user-delegated tasks through iterative interaction. Yet genuine interaction is inherently dynamic: users rarely specify their intent upfront, instead disclosing, revising, and reshaping it as the conversat

中文介绍 研究LLM在动态用户意图交互中的表现。发现模型难以处理用户中途变更、细化需求的情况，容易迷失。提出评估框架并揭示现有LLM在协作代理场景下意图追踪与回应的脆弱性，呼唤更鲁棒的交互设计。

Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction

👍 21

07/23 08:00

We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model leaderboard. At its core is a unified evaluation framework for constructing and running distribution-informed coding-agent

中文介绍 推出Tencent WorkBuddy Bench，多领域编码代理基准，采用抗污染任务构建方法。提供统一的评估框架与跨模型排行榜，聚焦真实多域编码场景，确保评测公平且可复现。

Self-Supervised Learning of Structured Dynamics from Videos

👍 18

07/23 08:00

Understanding motion in video is a fundamental challenge for visual learning, as frame-to-frame change entangles two sources of dynamics: camera motion and object motion. This decomposition has remained underexplored in representation learning, partly because these factors are tightly coupled in nat

中文介绍 提出从视频中自监督学习结构化动态，解耦相机运动与物体运动。通过设计表征学习框架，无需标注即可分离两种运动源，在动作识别和跟踪下游任务中显著提升性能。

Color Pass-Through via Camera-Display Coupling

👍 18

07/14 08:00

When a real-world scene is captured by a smartphone camera and viewed on its screen, the displayed image often differs noticeably from the original scene in color, brightness, and contrast. This gap persists despite substantial advances in both modern cameras and displays. A key reason is that most

中文介绍 针对手机拍摄与显示的颜色偏差，提出利用相机-显示耦合进行色彩传递。通过端到端建模拍摄到显示的光学链路，校正色彩、亮度和对比度，使屏幕呈现更接近真实场景。

Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models

👍 16

07/21 08:00

Injecting factual knowledge into large language models (LLMs) reliably and at scale remains an open challenge. Hypernetworks provide a promising solution to large-scale knowledge injection. Although hypernetworks are typically applied for test-time adaptation, we explore their use in train-time know

中文介绍 研究基于超网络的LLM知识注入缩放定律。超网络用于训练时注入事实知识，分析模型大小、知识量与注入效果的关系，发现随参数量增加，超网络能有效存储更多知识且不损害原始能力。

Beyond Euclidean Clipping: Overcoming Exploration Collapse in LLM RL via Riemannian Isometric Policy Optimization

👍 13

07/11 08:00

Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip are inherently limited by exploration collapse. Subsequent works remain primarily heuristic and fail to identify the essential cause of PPO-Clip's failure. This

中文介绍 揭示PPO-Clip在LLM强化学习中导致探索崩溃的根本原因，并提出黎曼等距策略优化（RIPO）。通过在策略空间的黎曼流形上实施等距裁剪，避免欧氏裁剪带来的坍塌，提升推理能力采样效率。

Sample-Efficient Learning from Agent Experience

👍 12

07/23 08:00

Real-world agent learning is often constrained by costly environment interactions, such as running time-consuming experiments or obtaining human feedback. In-context learning offers a highly sample-efficient way for agents to learn from their own interaction histories, but its gains disappear once t

中文介绍 提出样本高效的代理经验学习方法。利用上下文学习从代理自身交互历史中快速适应，但单次学习后增益消失。该方法通过经验重放与元学习，使代理能在少量交互中持续改进，显著降低环境交互成本。

Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers

👍 12

07/23 08:00

Multi-agent interactive world models should not only generate consistent observations, but also maintain world states that persist across agents and evolve across views. Existing autoregressive video diffusion pipelines carry forward observation history as conditioning context, which makes shared st

中文介绍 提出流式多智能体自回归扩散模型，引入世界状态寄存器以维护跨智能体的全局状态。在生成多视角视频时，寄存器同步状态演变，解决传统像素级自回归难以保持一致世界模型的问题。

Multi-Turn On-Policy Distillation with Prefix Replay

👍 9

07/16 08:00

We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multiple turns and a student imitates a teacher over these multi-turn interaction histories. Fully online OPD is costly because each update requires fresh student rollouts through the envir

中文介绍 研究多轮在线策略蒸馏（OPD），LLM代理与环境多轮交互，学生模仿教师的交互历史。提出前缀重放机制，缓存部分历史以减少完全在线rollout成本，在保持性能的同时显著提升训练效率。

Predictive Divergence Masks for LLM RL

👍 9

07/12 08:00

Reinforcement learning for large language models (LLMs) typically relies on trust-region masks to stabilize off-policy updates. The dominant PPO-style approach uses the sampled-token importance ratio for two criteria: a proximity criterion, which asks whether the policy has moved too far from the be

中文介绍 提出预测性发散掩码，用于LLM强化学习的信任域更新。相比PPO仅依赖重要性采样比率，该方法提前预测策略变化并调整掩码，更鲁棒地稳定离策略更新，在Reasoning基准上提升样本效率与最终性能。

DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations

👍 9

07/22 08:00

As autonomous agents rapidly evolve, their ability to reliably manipulate ubiquitous digital documents has become critical for enabling general-purpose AI assistants and automating complex workspace workflows. In this paper, we introduce DocOps, a deterministically verifiable evaluation framework un

中文介绍 引入DocOps，一个可确定性验证的基准，用于评估自主代理在复杂文档操作中的能力。包含文档编辑、表格处理等任务，通过严格验证确保执行正确，为通用AI助手提供可靠的评测平台。

Trajectory: A Standard Format for Agent Experience Data

@Letta_AI · 9.8K 粉丝 · 86.5K 阅 · 504 赞 · 31 转

07/24 14:07

Introducing trajectory, an open-source package that normalizes coding-agent sessions from @AnthropicAI Claude Code, @OpenAI Codex, @pidotdev, @LangChain deepagents, @openclaw, Letta Code, and other

中文介绍 Letta_AI 发布开源包 trajectory，标准化来自 Claude Code、Codex、Deep Agents 等平台的 coding-agent 会话数据，便于记录、复现与对比不同的 agent 行为。

Graph Engineering Clearly Explained

@akshay_pachaar · 282.5K 粉丝 · 66.4K 阅 · 515 赞 · 74 转

07/26 02:48

Loop engineering got about six weeks in the spotlight before the timeline moved on. On July 18, Peter Steinberger, the person behind OpenClaw, posted a nine-word question. "Are we still talking loops

中文介绍 回顾 loop 工程短暂流行后，graph 工程成为新焦点。Peter Steinberger 的提问引发对循环与图模型的讨论，本文清晰解释两者的核心差异与演进逻辑。

Why Software Factories Fail

@dexhorthy · 24.8K 粉丝 · 64.9K 阅 · 515 赞 · 50 转

07/25 00:51

or: the harness is not enough Update - the talk version of this post is live on youtube: https://www.youtube.com/watch?v=Ib5GBkD555M i guess we doin loops now We're all racing to put AI coding into production. A lot has

中文介绍 针对 AI 编码投入生产时的失败原因，指出仅靠 harness（控制框架）远远不够。结合视频版，分析软件工厂常见陷阱及如何避免。

Agent Harness Engineering vs. Loop Engineering vs. Graph Engineering

@beamnxw · 2.6K 粉丝 · 53.5K 阅 · 561 赞 · 92 转

07/25 22:25

A practical guide to the three architecture layers people keep mixing together The confusion is understandable. All three ideas sit around the same model, all three influence reliability, and all

中文介绍 实用指南区分 Agent Harness、Loop 与 Graph 三层架构。三者常被混淆，但各有侧重：Harness 负责编排，Loop 迭代执行，Graph 定义任务流向。

The new rules of context engineering for Claude 5 models

@trq212 · 318.0K 粉丝 · 48.6K 阅 · 1.2K 赞 · 119 转

07/25 01:45

I’ve written previously about how to best prompt the newest generation of Claude 5 models and work with them iteratively to discover what you want to build. But when you send a message to Claude, the

中文介绍 针对 Claude 5 模型的新一代上下文工程规则，讲解如何通过精心构造 prompt 和迭代交互，让模型更精准地理解需求并生成定制化结果。

Practical multi-agent orchestration in Codex

@pvncher · 30.4K 粉丝 · 44.0K 阅 · 565 赞 · 33 转

07/25 01:30

GPT-5.6 Sol gets especially interesting when it has a team to work with. Codex's new Multi-Agent V2 tools give Sol and Terra a natural way to delegate tasks, share updates, and coordinate through

中文介绍 Codex 多智能体 V2 实战：Sol 和 Terra 智能体通过任务委派、状态同步与协调调度，展示了多 agent 协作在复杂场景下的自然运行方式。

How we teach AI models

@leerob · 272.8K 粉丝 · 32.9K 阅 · 550 赞 · 51 转

07/24 09:39

How do AI models learn new skills and behaviors? The process is surprisingly human and easy to understand, even if you don’t have a machine learning background. Helpful colleagues AI models,

中文介绍 以通俗方式解释 AI 模型如何学习新技能和行为：类比人类协作与反馈过程，无需机器学习背景即可理解模型训练与迭代的基本原理。

[AINews] Claude Opus 5: Fable-level performance at Opus price (half Fable)

Latent Space · 07/25 15:25

ain't nobody beats Anthropic at distilling Fable!

中文介绍 Anthropic 发布 Claude Opus 5 模型，性能达到 Fable 级别但价格仅一半。模型 Epoch Capabilities Index 为 159，略低于 Fable 5 的 161，但其编码代理能力获好评。

Opus 5

Smol AI News · 07/24 13:44

**Anthropic** launched the **Claude Opus 5** model, which sparked mixed reactions including benchmark scrutiny and praise for its coding-agent capabilities. The model achieved an **Epoch Capabilities Index (ECI) of 159**, slightly below **Fable 5's 161**, but matched Fable 5 on software engineering

[AINews] Black Forest Labs FLUX 3 - Multimodal Flow Models that beat Seedance 2.0, Gemini Omni and Grok Imagine, and FLUX-mimic video-action robotics model

Latent Space · 07/24 12:30

A HUGE win for BFL!

中文介绍 Black Forest Labs 发布 FLUX 3 多模态流模型，性能超越 Seedance 2.0、Gemini Omni 和 Grok Imagine，并推出 FLUX-mimic 视频动作机器人模型。

ChatGPT Health 🩺, Fugu-Ultra 1.1 🐡, Runway Media Router 🎬

TLDR AI · 07/24 08:00

中文介绍 ChatGPT Health 功能上线，Fugu-Ultra 1.1 发布，Runway Media Router 亮相。

How AI helps scientists design the next generation of medicines

MIT Tech Review AI · 07/23 20:00

Designing and developing a new medicine is an expensive, failure-prone scientific challenge. A new drug can take many years to develop, at the cost of a significant investment. And even then, most possible candidates never reach the patient. For biologic medicines, therapies made from engineered pro

中文介绍 AI 助力科学家设计下一代药物。新药研发成本高、周期长、失败率高，多数候选药物无法惠及患者，AI 有望加速生物制剂的研发过程。

not much happened today

Smol AI News · 07/23 13:44

**The Stack v3** is released as the largest open code dataset with **114 TB raw data**, **224M repositories**, and **5T deduplicated tokens**, significantly expanding data for open code models and cyber-defense. The debate on **distillation** continues as a key ideological fault line, with calls for

中文介绍 The Stack v3 发布，成为最大开放代码数据集，含 114 TB 原始数据、2.24 亿仓库及 5T 去重令牌，扩展开放模型与网络防御数据。蒸馏（distillation）争论持续。

[AINews] "Laguna S 2.1 Released: Cheaper than Deepseek v4 Flash, Better than V4 Pro"

Latent Space · 07/23 13:18

a quiet day lets us highlight a new neolab win.

中文介绍 Laguna S 2.1 发布，价格低于 Deepseek v4 Flash，性能优于 V4 Pro，为 neolab 的新成果。

Inside the Model Factory — Eiso Kant, Poolside AI

Latent Space · 07/23 13:09

Poolside's co-CEO on how his small team of top researchers built a model factory capable of training Laguna S - a 118B MOE beating Thinky's ~1T open weights model... and this is just the beginning.

中文介绍 Poolside AI 联合 CEO Eiso Kant 介绍其团队打造模型工厂，训练出 118B 参数 MOE 模型 Laguna S，击败 Thinky 约 1T 参数的开放权重模型，这仅是开始。

Launching Health in ChatGPT

OpenAI News · 07/23 08:00

Health in ChatGPT now lets eligible U.S. users securely connect medical records and Apple Health to get more personalized insights and better understand their health.

中文介绍 OpenAI 在 ChatGPT 中推出 Health 功能，符合条件的美国用户可安全连接医疗记录和 Apple Health，获得个性化健康洞察。

Bringing Nunchaku 4-bit Diffusion Inference to Diffusers

Hugging Face Blog · 07/23 08:00

中文介绍 Hugging Face Diffusers 集成 Nunchaku 4-bit 扩散推理，优化模型推理效率。

Cursor Router 🔀, OpenAI Presence 🤖, AMD + Anthropic deal 🤝🏻

TLDR AI · 07/23 08:00

中文介绍 Cursor Router 发布，OpenAI Presence 上线，AMD 与 Anthropic 达成合作交易。

Accelerating the frontiers of scientific discovery: Google’s $40M commitment to the Genesis Mission

DeepMind Blog · 07/22 21:38

Google commits $40M in AI tokens and credits for the Genesis Mission

中文介绍 Google 承诺向 Genesis 任务提供 4000 万美元的 AI 代币和信用额度，以加速科学发现前沿。

Building AI infrastructure with the Effingham County community

OpenAI News · 07/22 21:00

OpenAI announces Project Camellia in Effingham County, Georgia, with commitments to responsible energy, community investment, jobs, and access to Codex.

中文介绍 OpenAI 在佐治亚州 Effingham 县启动 Project Camellia，承诺负责任能源、社区投资、就业及 Codex 访问。

How news organizations are using AI to advance their vital missions

OpenAI News · 07/22 21:00

News organizations are using AI to strengthen reporting, grow audiences, and improve business operations, with OpenAI tools supporting journalists and publishers worldwide.

中文介绍 新闻机构利用 AI 加强报道、扩大受众、改善运营。OpenAI 工具正在全球支持记者和出版商。

Advancing the next era of national science

OpenAI News · 07/22 20:00

OpenAI outlines its commitment to advancing American science working with the U.S. Department of Energy and national labs to use frontier AI to accelerate discovery.

中文介绍 OpenAI 概述其与美国能源部及国家实验室合作，利用前沿 AI 加速科学发现，推动美国科学事业。